© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 175600
    Prev
    Next
    INDEX
    Explanations

    toil

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    egin
    0.37
    ostino
    0.36
    篙
    0.36
    起來
    0.35
     അപ
    0.35
    ھے
    0.35
     lept
    0.35
     gcd
    0.34
     sarcoma
    0.34
    鲨
    0.33
    POSITIVE LOGITS
     To
    1.75
     то
    1.66
    To
    1.60
     TO
    1.56
     तो
    1.51
     تو
    1.46
    TO
    1.37
     toil
    1.36
     То
    1.32
     তো
    1.27
    Activations Density 0.012%

    No Known Activations